WWW.DISSERTATION.XLIBX.INFO
FREE ELECTRONIC LIBRARY - Dissertations, online materials
 
<< HOME
CONTACTS



Pages:   || 2 | 3 | 4 | 5 |   ...   | 10 |

«MULTILAYER BACKGROUND MODELING UNDER OCCLUSIONS FOR SPATIO-TEMPORAL SCENE ANALYSIS A Dissertation Presented to The Academic Faculty By Shoaib Azmat ...»

-- [ Page 1 ] --

MULTILAYER BACKGROUND MODELING UNDER

OCCLUSIONS FOR SPATIO-TEMPORAL SCENE

ANALYSIS

A Dissertation

Presented to

The Academic Faculty

By

Shoaib Azmat

In Partial Fulfillment

of the Requirements for the Degree

Doctor of Philosophy

in

Electrical and Computer Engineering

School of Electrical and Computer Engineering

Georgia Institute of Technology

August 2014

Copyright © 2014 by Shoaib Azmat

MULTILAYER BACKGROUND MODELING UNDER

OCCLUSIONS FOR SPATIO-TEMPORAL SCENE

ANALYSIS

Approved by:

Dr. Linda Wills, Advisor Dr. Bo Hong School of ECE School of ECE Georgia Institute of Technology Georgia Institute of Technology Dr. Aaron Lanterman Dr. Scott Wills, Co-Advisor School of ECE (Posthumous) Georgia Institute of Technology School of ECE Georgia Institute of Technology Dr. Jeffrey Vetter Dr. James Hamblen College of Computing Georgia Institute of Technology School of ECE Georgia Institute of Technology Date Approved: June 10, 2014 In memory of Dr. Scott Wills

ACKNOWLEDGMENTS

First, I want to express my gratitude to my advisor Dr. Linda Wills for all her support, guidance, and patience during my doctoral research. Thank you Dr. Linda, without your support and encouragement in difficult times, I wouldn’t have made it. I want to thank my late advisor Dr. Scott Wills for the time I spent with him. Dr. Scott, you left us so soon, and there were many things that I wanted to talk about with you. However, I am deeply grateful to you as they were your initial ideas that shaped my research. I thank you for giving me a great learning platform, which put me on track towards achieving my goal. You will be in my memories for ever as an exceptional mentor and friend.

I am grateful to Dr. James Hamblen, Dr. Bo Hong, Dr Aaron Lanterman, and Dr.

Jeffrey Vetter for serving on my committee, and for providing valuable feedback and suggestions. I want to thank the Higher Education Commission of Pakistan and the Fulbright Program of USA for giving me scholarship, to pursue my graduate studies. I also want to thank my colleagues of the MOVES Lab at Georgia Tech, Dr. Dana Forsthoefel and Qianao Ju, for their support and company.

In the end, I want to thank my parents, R D Khan and M J Khan, and my siblings R Azmat, B Azmat, S Azmat, N Azmat, A Khan, H Khan, and R Khan. Their support and encouragement always acted as a catalyst for achieving my goals.

–  –  –

Figure 4 Unimodal vs multimodal background modeling.............. 18 Figure 5 Traditional vs two-layer background modeling.............. 21 Figure 6 Two-layer background modeling pixel-level................ 21 Figure 7 Need for multi-layer background modeling................ 23

–  –  –

Figure 11 Ghost removal based on three histograms................. 32 Figure 12 Changing background scenario: (a) Original BG (b) Brown box added (c) Red box added (use main background layer (a) to calculate H2 and H3) 32

–  –  –

Figure 14 Abandoned object detection in a crowded scene at different points in time 37 Figure 15 Blocks added and removed at different points in time, a red circle indicates new entries while blue indicates the ones already there, a black circle indicates the objects removed while white indicates the ones removed from the initial background: (a) Initial background (b) Three blocks added (c) Three more blocks added, three removed including one from initial background (d) Three more blocks added.......... 37 Figure 16 Object layer removal based on occlusion reasoning: (a) Brown box added (b) Red box added occluding brown box (c) Brown box removed (d) Brown box added occluding red box.................... 38 Figure 17 Occlusion reasoning effect: (a) Original image (b) Ground truth (c) Pixelbased [1] (d) Pixel-based [2] (e) Object-based [TM3]........... 38

–  –  –

Figure 19 Pixel vs. object-based modeling: (a) Original image (b) Ground truth (c) Pixel-based [1] (d) Pixel-based [2] (e) Object-based [TM3]........ 39 Figure 20 Outdoor cars, filtering at 50% observability threshold: (a) Original image (b) Ground truth (c) Unfiltered (d) Filtered.............. 41 Figure 21 Indoor boxes, filtering at 50% observability threshold: (a) Original image (b) Ground truth (c) Unfiltered (d) Filtered.............. 41 Figure 22 Outdoor cars: (a) Total number of pixel errors at 50% observability (b) FP vs TP at 50% observability (c) % Observability vs. no. of layer errors 42 Figure 23 Indoor boxes: (a) Total number of pixel errors at 50% observability (b) FP vs TP at 50% observability (c) % Observability vs. no. of layer errors 43

–  –  –

Figure 26 Spatial displacement scenarios: Scenario1, moved object from original background; Scenario2, moved object; Scenario3, partially displaced object; Scenario4, partially occluded object................. 51 Figure 27 A change in a bag position has been recognized.............. 51 Figure 28 An object distance with itself dist(PP) and a different object dist(PQ) in the four scenarios: (a) 64-bin histogram (b) 512-bin histogram (c) 4096-bin histogram............................. 52

–  –  –





Figure 31 Un-coalesced array of structures (left), coalesced structure of arrays (right) 61 Figure 32 Asus AT3IONT-I NVIDIA ION GPU platform.............. 65

–  –  –

Figure 34 Speed ups over a single core of Atom CPU as a result of various performance optimizations, cumulatively applied left to right.......... 67 Figure 35 Speed ups for different number of pixels per thread implementations over a single pixel per thread implementation.................. 67

–  –  –

Figure 39 TM3 speed bottlenecks temporarily removed for testing (column 2-4) results in higher fraction of the MMM speed for TM3 on ION GPU, the first & last column again show TM3 speed as a fraction of MMM on ION and Atom respectively from the previous figure........... 72

–  –  –

This dissertation presents an efficient multi-layer background modeling approach to distinguish among midground objects, the objects whose existence occurs over varying time scales between the extremes of short-term ephemeral appearances (foreground) and longterm stationary persistences (background). The dissertation consists of three contributions.

In the first contribution, a multilayer object-based background modeling technique, called temporal multimodal mean TM3, is presented for video surveillance. The technique temporally models a scene in which there are multiple interacting midground objects occurring at different time scales. The approach correctly models scenes with long-term occlusions and ghost objects as compared to the multilayer pixel-based background modeling approaches. TM3 technique represents a scene, with multiple midground objects entering, leaving, and occluding each other at different points in time. This leads to richer information about temporal properties of a scene than traditional foreground/background segmentation. The information includes when a particular object arrived or left the scene, and the occlusion relationships among different objects while they are in the scene.

The multi-layer (and two-layer) background modeling techniques that model objects that have become stationary will incorrectly detect a new object if an existing midground or background object is displaced. The second contribution presents a novel spatio-temporal reasoning mechanism, called spatio-temporal multimodal mean STM3, based on multilayer background modeling and objects appearances to conserve the state of moved objects in a scene. The algorithm is an extension of our temporal multimodal mean TM3 algorithm to spatial analysis. The STM3 algorithm, consistently models midground/background objects upon partial/full change of position, and maintains conservation of existing objects, only removing them once they leave the scene. An important feature of this algorithm is that it avoids false detections of new objects when existing objects are displaced in the scene.

–  –  –

balance accuracy, speed, and power. Due to its inherent parallelism, robust adaptive background modeling, such as the Gaussian mixture model (GMM), has been implemented on graphical processing units (GPUs) with significant performance improvements over CPUs.

However, these implementations are infeasible in embedded applications due to the high power ratings, in the range of 100 watts, of the targeted general-purpose NVIDIA GeForce GPU platforms. The third contribution focuses on how data and thread-level parallelism is exploited and memory access patterns are optimized to target a low-cost robust adaptive background modeling algorithm multimodal mean (MMM) to a low-power GPU NVIDIA ION with thermal design power (TDP) of only 12 watts. The algorithm has comparable accuracy with the GMM algorithm, but less computational cost. Accelerating this technique is also important because it is at the core of our spatio-temporal multi-layer background modeling algorithms TM3/STM3. We have achieved a frame rate of 392fps with a full VGA resolution (640x480) frame on the NVIDIA ION GPU. This is a 20X speed-up of the MMM algorithm on the GPU compared to the embedded CPU platform Intel Atom of comparable TDP. Moreover, our GPU implementation of MMM outperforms the GPU implementation of GMM by achieving a speed up of 6x. Subsequently, we extended the MMM GPU implementation to our multi-layer background modeling algorithm TM3, and achieved 5x speed up over the Atom CPU implementation.

–  –  –

The demand for video surveillance systems in public places and industry has increased dramatically. A recent survey shows that an estimated 1.85 million surveillance cameras have been deployed in the United Kingdom alone [3]. Many modern cities now have a network of surveillance cameras, deployed across metropolitan regions by multiple coordinated public/private agencies. These cameras are used in places such as streets, airports, subway stations, malls, and offices to detect abnormal activity. This enables many public safety applications including intruder detection, abandoned object detection, people counting, and traffic violation detection. Cameras are also extensively deployed in industry for process monitoring and product inspection, and in health facilities for improved patient care such as fall detection.

Requiring human operators to monitor video feeds is tedious, error prone, and simply infeasible. Advances in video technology has made automated video surveillance systems attractive in reducing the burden and tedium of manual monitoring. The desirability of portable and low-cost automated video surveillance systems, for example in outdoor settings, has led to the emergence of embedded smart surveillance cameras. These cameras have limited available power and computational resources, demanding efficient low-cost algorithms.

A core problem in automated visual surveillance is background modeling. This is the problem of separating salient, moving foreground from uninteresting, stationary background. Traditional background modeling divides a given scene into foreground and background regions. However, the real world can be much more complex than this simple classification, and object appearance events often occur over varying time scales. There are situations in which objects appear on the scene at different points in time and become stationary; these objects can get occluded by one another, and can change positions or be removed from the scene. Inability to deal with such scenarios involving midground objects results in errors, such as ghost objects (when newly revealed background, due to removal of an object, is mistaken as a new midground object), miss-detection of overlapping objects, and aliasing caused by the objects that have left the scene but are not removed from the model. Modeling temporal layers of multiple objects can overcome these errors, and enables the surveillance of scenes containing multiple midground objects.

This dissertation is focused on modeling temporal layers of multiple objects and it specifically targets embedded surveillance systems, requiring a real-time, energy efficient and low-cost solution. One approach is to model these multiple midground objects using a tracking algorithm, but the computational cost is prohibitively high for applications in a resource-constrained embedded environment. This dissertation pursues the goal of efficiently modeling multiple midground objects using layers of low-cost background modeling, and discusses the challenges that arise in achieving this goal.

A few existing pixel-based approaches attempt to address this challenge by maintaining multiple layers [1], [4]. However, the problem with pixel-based modeling is that it is unable to deal with 1) long-term occlusions, and 2) ghost objects created by movement of objects in the original background. On a pixel level, one can delete object pixels not seen for a long time, but doing so will result in a new object in the scene if that object reappears.

If an occluded pixel is not deleted, even if it has been occluded for a long period, then if the occluded object moves out of the scene, the pixel will remain in the model which will take extra space, and cause aliasing with overlapping objects. In addition, at the pixel level, it is difficult to reason about the order of occlusion among objects, and to suppress ghost objects created by movement of objects in the original background. Moreover, if an original background object is moved to a different location in a scene, then the existing multi-layer background modeling techniques will detect a new object at the new location in addition to a ghost object at the original location.



Pages:   || 2 | 3 | 4 | 5 |   ...   | 10 |


Similar works:

«Characterization of the Roles of TopoIIIα-RMI1 in Maintaining Genome Integrity by Jay Tun-Chieh Yang A thesis submitted in conformity with the requirements for the degree of Doctor of Philosophy Graduate Department of Biochemistry University of Toronto © Copyright by Jay Tun-Chieh Yang (2012) Characterization of the roles of TopoIIIα-RMI1 in maintaining genome integrity Doctor of Philosophy, 2012; Jay Tun-Chieh Yang; Department of Biochemistry, University of Toronto Abstract Bloom syndrome...»

«UNIVERSITÀ DEGLI STUDI DI NAPOLI “FEDERICO II” FACOLTÀ DI INGEGNERIA DOTTORATO IN INGEGNERIA DEI MATERIALI E DELLE STRUTTURE XXIV CICLO TOWARD A NEW THERMOPLASTIC EPOXY-BASED SYSTEM: NANOCOMPOSITE AND FIBRE REINFORCED MATERIAL BY REACTIVE PROCESSING Ph.D. Dissertation Candidate: Angelo Petriccione TUTOR: PROF. ING. MICHELE GIORDANO CO-TUTOR: DOTT. ING. MAURO ZARRELLI COORDINATOR: PROF. ING. GIUSEPPE MENSITIERI DECEMBER 2011 This thesis is submitted in fulfilment of the requirements for...»

«The List as Treasury in the Greek World By Athena E. Kirk A dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy in Classics in the Graduate Division of the University of California, Berkeley Committee in charge: Professor Leslie V. Kurke, Chair Professor Andrew Garrett Professor Nikolaos Papazarkadas Professor Ronald S. Stroud Fall 2011 Abstract The List as Treasury in the Greek World by Athena E. Kirk Doctor of Philosophy in Classics...»

«Towards an Existential Approach to the Meaning of Work By Scott MacMillan A Thesis Submitted to Saint Mary‟s University, Halifax, Nova Scotia in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy August, 2009, Halifax, Nova Scotia Copyright Scott MacMillan, 2009 Approved: Dr. Albert J. Mills Supervisor Approved: Dr. Jean Helms-Mills Reader Approved: Dr. Rick Hudson Reader Approved: Dr. Roger Wehrell Reader Approved: Dr. Scott Taylor Examiner Date: August 10, 2009...»

«MINERALOGY OF DUST EMISSIONS FROM THE BODELE DEPRESSION By ROSEMARY ASSUNTA MILLHAM Bachelor of Science State University of New York at New Paltz New Paltz, NY 1983 Master of Science in Education State University of New York at New Paltz New Paltz, NY 1987 Submitted to the Faculty of the Graduate College of the Oklahoma State University in partial fulfillment of the requirements for the Degree of DOCTOR OF PHILOSOPHY July, 2007 MINERALOGY OF DUST EMISSIONS FROM THE BODELE DEPRESSION...»

«Service Introduction in an Active Network by David J. Wetherall E.E. Massachusetts Institute of Technology 1995 S.M. Massachusetts Institute of Technology 1994 B.E. University of Western Australia 1989 Submitted to the Department of Electrical Engineering and Computer Science in partial ful llment of the requirements for the degree of Doctor of Philosophy at the Massachusetts Institute of Technology February 1999 c Massachusetts Institute of Technology 1998. All rights reserved. Author....»

«POPULAR SPIRITUALITY AS CULTURAL ENERGY Albert E. Alejo, SJ I. INTRODUCTION Let me start with a few personal notes, hoping that in the process I could slide slowly into my topic of “Popular Spirituality as Cultural Energy”. First of all, I am happy to be back in UST. This is my alma mater. I started here in biochemistry because I wished to become a scientist. The other side of me, however, wanted to become a priest. Although in theory I could combine both scientist and priest within the...»

«Department of Computer Science Hamilton, New Zealand Concept-based text clustering by Lan Huang This thesis is submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science at The University of Waikato April 2011 c ￿ 2011 Lan Huang Abstract Thematic organization of text is a natural practice of humans and a crucial task for today’s vast repositories. Clustering automates this by assessing the similarity between texts and organizing them...»

«IMPROVEMENTS FOR CHIP-CHIP INTERCONNECTS AND MEMS PACKAGING THROUGH MATERIALS AND PROCESSING RESEARCH A Dissertation Presented to The Academic Faculty by Erdal Uzunlar In Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the School of Chemical & Biomolecular Engineering Georgia Institute of Technology May 2015 COPYRIGHT© 2015 BY ERDAL UZUNLAR IMPROVEMENTS FOR CHIP-CHIP INTERCONNECTS AND MEMS PACKAGING THROUGH MATERIALS AND PROCESSING RESEARCH Approved by: Dr. Paul...»

«Top ten blogs November 2015 by Bart Nooteboom 19. Beyond nihilism: Imperfection on the move published 10-8-2012 The philosopher Nietzsche dealt a death blow to belief in old absolutes, raising the spectre of nihilism. God is dead, and truth, morality and beauty have become subjective, relative and evanescent. There is weak nihilism: regretful loss of belief, and strong nihilism: no longer seeing such belief as desirable. Could we not see the loss of old absolutes as a discarding of shackles, an...»

«PERCEPTIONS AND EXPERIENCES OF THE SOCIALIZATION PROCESSES AMONG EARLY CAREER FOREIGN NATIONAL TENURE-ACCRUING FACULTY IN A RESEARCH I UNIVERSITY By MUEEN AIZAZ ZAFAR A DISSERTATION PRESENTED TO THE GRADUATE SCHOOL OF THE UNIVERSITY OF FLORIDA IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY UNIVERSITY OF FLORIDA © 2011 Mueen Aizaz Zafar This work is dedicated to my mother, brothers, and sisters for making it possible for me to get this far despite losing my...»

«MODELING, DESIGN AND ENERGY MANAGEMENT OF FUEL CELL SYSTEMS FOR AIRCRAFT A Dissertation Presented to The Academic Faculty by Thomas Heenan Bradley In Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the School of Mechanical Engineering Georgia Institute of Technology December, 2008 Copyright © Thomas Heenan Bradley 2008 MODELING, DESIGN AND ENERGY MANAGEMENT OF FUEL CELL SYSTEMS FOR AIRCRAFT Approved by: Dr. David E. Parekh, Advisor Dr. William J. Wepfer School of...»





 
<<  HOME   |    CONTACTS
2016 www.dissertation.xlibx.info - Dissertations, online materials

Materials of this site are available for review, all rights belong to their respective owners.
If you do not agree with the fact that your material is placed on this site, please, email us, we will within 1-2 business days delete him.